Camera calibration from very few images based on soft constraint optimization
作者: Hongjun ZhuYan LiXin LiuXuehui YinYanhua ShaoYing QianJindong Tan
作者单位: 1School of Software Engineering, Chongqing University of Posts and Telecommunications, Chongqing City, 400065, China
2Department of Mechanical, Aerospace, and Biomedical Engineering, University of Tennessee, Knoxville, 37919, USA
3School of Information Engineering, Southwest University of Science and Technology, Mianyang, 621010, China
4Chongqing Engineering Research Center of Software Quality Assurance, Testing and Assessment, Chongqing 400065, China
刊名: Journal of the Franklin Institute, 2020, Vol.357 (4), pp.2561-2584
来源数据库: Elsevier Journal
DOI: 10.1016/j.jfranklin.2020.02.006
原始语种摘要: Abstract(#br)Camera calibration is a basic and crucial problem in photogrammetry and computer vision. Although existing calibration techniques exhibit excellent precision and flexibility in classical cases, most of them need from 5 to 10 calibration images. Unfortunately, only a limited number of calibration images and control points can be available in many application fields such as criminal investigation, industrial robot and augmented reality. For these cases, this paper presented a two-step calibration based on soft constraint optimization, which is motivated by "no free lunch" theorem and error analysis. The key steps include (1) homography estimation with weighting function, (2) Initialization based on a simplified model, and (3) soft constraint optimization in terms of...
全文获取路径: Elsevier  (合作)
影响因子:2.418 (2012)

  • calibration 校准
  • based 基于
  • constraint 约束
  • optimization 最佳化
  • error 误差
  • homography 同形异义性
  • augmented 增加的
  • precision 精度
  • flexibility 柔顺性
  • criminal 刑事